© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2641
    Prev
    Next
    INDEX
    Explanations

    text relating to specific medicinal and scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéro
    -0.37
    baseline
    -0.34
    SuppressLint
    -0.33
    Попис
    -0.33
    bay
    -0.33
    Bay
    -0.33
    AccessorTable
    -0.33
    salms
    -0.32
    bone
    -0.32
    NamedQuery
    -0.32
    POSITIVE LOGITS
     BR
    2.16
     Br
    2.05
     br
    2.05
    BR
    1.94
    Br
    1.94
     브
    1.86
    br
    1.83
     bra
    1.70
     Bra
    1.68
    Bra
    1.62
    Activations Density 2.850%

    No Known Activations